Generating Enhanced Negatives for Training Language-Based Object Detectors

 

Publication Date: 6/17/2024

Event: CVPR 2024

Reference: pp. 13592-13602, 2024

Authors: Shiyu Zhao, Rutgers University; Long Zhao, Google Research; Vijay Kumar B.G., NEC Labs America; Yumin Suh, NEC Labs America; Dimitris N. Metaxas, Rutgers University; Manmohan Chandraker, NEC Labs America & UC San Diego; Samuel Schulter, NEC Labs America

Abstract: The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative samples. However, the free-form nature and the open vocabulary of object descriptions make the space of negatives extremely large. Prior works randomly sample negatives or use rule-based techniques to build them. In contrast, we propose to leverage the vast knowledge built into modern generative models to automatically build negatives that are more relevant to the original data. Specifically, we use large-language-models to generate negative text descriptions, and text-to-image diffusion models to also generate corresponding negative images. Our experimental analysis confirms the relevance of the generated negative data, and its use in language-based detectors improves performance on two complex benchmarks.

Code is available at: https://github.com/xiaofeng94/Gen-Enhanced-Negs

Publication Link: https://openaccess.thecvf.com/content/CVPR2024/html/Zhao_Generating_Enhanced_Negatives_for_Training_Language-Based_Object_Detectors_CVPR_2024_paper.html

Additional Publication Link: https://arxiv.org/abs/2401.00094